© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 30707
    Prev
    Next
    INDEX
    Explanations

    philosophers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vũ
    -0.07
     праців
    -0.07
     gas
    -0.06
    iveness
    -0.06
     joins
    -0.06
    -less
    -0.06
     Phen
    -0.06
     Youth
    -0.06
    дами
    -0.06
     clientes
    -0.06
    POSITIVE LOGITS
    orgetown
    0.07
     Berkshire
    0.07
     compare
    0.06
    invoke
    0.06
     Pars
    0.06
     крок
    0.06
    lf
    0.06
    õi
    0.06
     церков
    0.06
     destabil
    0.06
    Activations Density 0.024%

    No Known Activations